Title :
Research on fast training algorithm for recurrent neural network
Author :
Gong, Dunwei ; Xu, Shifan ; Sun, Xiaoyan
Author_Institution :
Coll. of Inf. & Electr. Eng., China Univ. of Mining & Technol., Jiangsu, China
Abstract :
In this paper, strategy on training recurrent neural networks based on genetic algorithms is expounded, which includes several key issues in designing a genetic algorithm, choice of running parameters and diagram of training method. Then forecasting nonlinear system using recurrent neural network is present. Simulation shows the method is effective
Keywords :
genetic algorithms; learning (artificial intelligence); recurrent neural nets; fast training algorithm; genetic algorithms; nonlinear system forecasting; recurrent neural network; running parameters; Algorithm design and analysis; Control system synthesis; Educational institutions; Genetic algorithms; Genetic mutations; Neurons; Nonlinear control systems; Nonlinear systems; Recurrent neural networks; Sun;
Conference_Titel :
Industrial Electronics, 2001. Proceedings. ISIE 2001. IEEE International Symposium on
Conference_Location :
Pusan
Print_ISBN :
0-7803-7090-2
DOI :
10.1109/ISIE.2001.931831
